Description
execute a query statement on a Hive table which contains decimal data type field, than save the result into tachyon as parquet file, got error as below:
java.lang.RuntimeException: Unsupported datatype DecimalType()
at scala.sys.package$.error(package.scala:27)
at org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$fromDataType$2.apply(ParquetTypes.scala:343)
at org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$fromDataType$2.apply(ParquetTypes.scala:292)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.sql.parquet.ParquetTypesConverter$.fromDataType(ParquetTypes.scala:291)
at org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$4.apply(ParquetTypes.scala:363)
at org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$4.apply(ParquetTypes.scala:362)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at org.apache.spark.sql.parquet.ParquetTypesConverter$.convertFromAttributes(ParquetTypes.scala:361)
at org.apache.spark.sql.parquet.ParquetTypesConverter$.writeMetaData(ParquetTypes.scala:407)
at org.apache.spark.sql.parquet.ParquetRelation$.createEmpty(ParquetRelation.scala:151)
at org.apache.spark.sql.parquet.ParquetRelation$.create(ParquetRelation.scala:130)
at org.apache.spark.sql.execution.SparkStrategies$ParquetOperations$.apply(SparkStrategies.scala:204)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
at org.apache.spark.sql.catalyst.planning.QueryPlanner$$anonfun$1.apply(QueryPlanner.scala:58)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at org.apache.spark.sql.catalyst.planning.QueryPlanner.apply(QueryPlanner.scala:59)
at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan$lzycompute(SQLContext.scala:417)
at org.apache.spark.sql.SQLContext$QueryExecution.sparkPlan(SQLContext.scala:415)
at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan$lzycompute(SQLContext.scala:421)
at org.apache.spark.sql.SQLContext$QueryExecution.executedPlan(SQLContext.scala:421)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:424)
at org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:424)
at org.apache.spark.sql.SchemaRDDLike$class.saveAsParquetFile(SchemaRDDLike.scala:76)
at org.apache.spark.sql.SchemaRDD.saveAsParquetFile(SchemaRDD.scala:103)
at com.jd.jddp.spark.hive.Cache$.cacheTable(Cache.scala:33)
at com.jd.jddp.spark.hive.Cache$$anonfun$main$5.apply(Cache.scala:61)
at com.jd.jddp.spark.hive.Cache$$anonfun$main$5.apply(Cache.scala:59)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:772)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:771)
at com.jd.jddp.spark.hive.Cache$.main(Cache.scala:59)
at com.jd.jddp.spark.hive.Cache.main(Cache.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
at java.lang.reflect.Method.invoke(Method.java:597)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:459)
Attachments
Issue Links
- duplicates
-
SPARK-4176 Support decimals with precision > 18 in Parquet
-
- Resolved
-